2 citations · 3 across the 4 of their papers we have counts for
5 papers
ShutterMuse: Capture-Time Photography Guidance with MLLMs
Jiayu Li, Yixiao Fang, Tianyu Hu +5
Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet existing aesthetic cropping benchmarks mainly evaluate post-hoc crop prediction…
WildQA: In-the-Wild Video Question Answering
Santiago Castro, Naihao Deng, Pingxuan Huang +2
Existing video understanding datasets mostly focus on human interactions, with little attention being paid to the "in the wild" settings, where the videos are recorded outdoors. We…
Cross-domain Trajectory Prediction with CTP-Net
Pingxuan Huang, Zhenhua Cui, Jing Li +3
Most pedestrian trajectory prediction methods rely on a huge amount of trajectories annotation, which is time-consuming and expensive. Moreover, a well-trained model may not effect…
FIBER: Fill-in-the-Blanks as a Challenging Video Understanding Evaluation Framework
Santiago Castro, Ruoyao Wang, Pingxuan Huang +5
We propose fill-in-the-blanks as a video understanding evaluation framework and introduce FIBER -- a novel dataset consisting of 28,000 videos and descriptions in support of this e…
FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation
Wenhao Zhu, Shujian Huang, Tong Pu +6
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which i…